Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Addressing the user

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ton
    -0.07
     Rouge
    -0.07
    esting
    -0.07
    moire
    -0.06
    EV
    -0.06
     AAP
    -0.06
     gửi
    -0.06
     Gn
    -0.06
    _spacing
    -0.06
    maxlength
    -0.06
    POSITIVE LOGITS
    .translation
    0.06
    شنبه
    0.06
     remark
    0.06
     réuss
    0.06
    excel
    0.06
     WX
    0.06
     aston
    0.06
    .Assertions
    0.05
    jourd
    0.05
     flesh
    0.05
    Act Density 0.164%

    No Known Activations